{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:18:19Z","timestamp":1761581899717,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1109\/itsc.2019.8917002","type":"proceedings-article","created":{"date-parts":[[2019,11,29]],"date-time":"2019-11-29T11:11:50Z","timestamp":1575025910000},"page":"3176-3181","source":"Crossref","is-referenced-by-count":15,"title":["Lane-Merging Using Policy-based Reinforcement Learning and Post-Optimization"],"prefix":"10.1109","author":[{"given":"Patrick","family":"Hart","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonard","family":"Rychly","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Emergence of Locomotion Behaviours in Rich Environments","author":"heess","year":"2017","journal-title":"CoRR"},{"key":"ref11","first-page":"1856","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"haarnoja","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018"},{"key":"ref12","article-title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","author":"shalev-shwartz","year":"2016","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569448"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05816-6"},{"key":"ref15","first-page":"1","article-title":"Guided Policy Search","author":"levine","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning"},{"article-title":"Local minima in training of neural networks","year":"2016","author":"swirszcz","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2015.7225909"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500363"},{"article-title":"Divine-RL: an autonomous driving environment for applied reinforcement learning","year":"2019","author":"hart","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref6","article-title":"Maximum a Posteriori Policy Optimisation","author":"abdolmaleki","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref8","article-title":"Proximal Policy Optimization Algorithms","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref7","first-page":"1889","article-title":"Trust Region Policy Optimization","author":"schulman","year":"0","journal-title":"Proceedings of The 32nd International Conference on Machine Learning"},{"journal-title":"Vehicle Dynamics and Control","year":"2011","author":"rajamani","key":"ref2"},{"key":"ref1","first-page":"369","article-title":"Generalization in Reinforcement Learning: Safely Approximating the Value Function","volume":"7","author":"boyan","year":"1994","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Learnings Options End-to-End for Continuous Action Tasks","author":"klissarov","year":"2017","journal-title":"CoRR"},{"article-title":"Ceres Solver","year":"0","author":"agarwal","key":"ref20"}],"event":{"name":"2019 IEEE Intelligent Transportation Systems Conference - ITSC","start":{"date-parts":[[2019,10,27]]},"location":"Auckland, New Zealand","end":{"date-parts":[[2019,10,30]]}},"container-title":["2019 IEEE Intelligent Transportation Systems Conference (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8907344\/8916833\/08917002.pdf?arnumber=8917002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:48:54Z","timestamp":1658155734000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8917002\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/itsc.2019.8917002","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}